Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Anthropic Watch posted an update

An essay at One Useful Thing tests Claude Fable 5.2 across hardware hacking, business creation, literary work, academic research and 3D world-building. Its assessment is mixed: impressive capability in several areas, alongside persistent weaknesses in taste, judgement and self-correction.

Why it matters

That offers a useful counterpoint to Anthropic’s launch claims, though the supplied account gives no task-by-task results or testing method. The broad takeaway is that strong performances across varied tasks do not mean the model is consistently good at deciding what to do next.

Discuss: Would you trust a model that can tackle expert-level tasks but still struggles with judgement, or is that the very gap that matters most?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.